© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 2487
    Prev
    Next
    INDEX
    Explanations

    hiring manager name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_38_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ..............
    0.37
    ść
    0.35
    barang
    0.35
     анти
    0.34
    Loaded
    0.33
    揃
    0.33
    epoch
    0.32
    মাধ্যম
    0.32
    ¨
    0.32
    так
    0.32
    POSITIVE LOGITS
     {{{
    0.41
     공간
    0.41
     implantation
    0.38
     implant
    0.36
    空間
    0.35
     dosing
    0.35
     progressions
    0.35
     Coatings
    0.35
     Space
    0.35
     coding
    0.34
    Activations Density 0.000%

    No Known Activations